API Rate Limits Compared: Every Major LLM Provider (May 2026)

Fourth edition. The third (April 2026) covered 17 providers. This update reflects model changes since April — GPT-5.5 Instant, Qwen3.7-Max, Command A+ — and structural updates at Anthropic, Alibaba, and Cohere.

What changed since April
Free Tier — RPM & RPD
Free Tier — TPM & TPD
Entry Paid Tier — RPM & RPD
Entry Paid Tier — TPM
Scaled Tier — RPM & TPM
Cerebras & SambaNova
Audio Models — ASH & ASD
Cloud Aggregators — Azure AI & AWS Bedrock
More Providers — Perplexity, Alibaba, Moonshot
Provider Notes
Tips for managing rate limits

Last updated: May 23, 2026.

What changed since April

New and updated models:

OpenAI: GPT-5.5 Instant (May 5) is now the default free-tier ChatGPT model, replacing GPT-5.3 Instant. GPT-5.5 Instant sits in the same rate limit pool as GPT-5.5 on paid tiers. GPT-5.2 is being phased out; GPT-5.1 no longer available. GPT-5.4-Cyber added for vetted security teams — rate limits not publicly disclosed. GPT-4.1 Nano remains the budget/high-throughput option.
Anthropic: No new flagship since Opus 4.7 (April 16). Claude 3 Haiku retired April 2026. Rate limit structure unchanged since April.
Google: Gemini 3.1 Pro (Feb 19) remains current flagship. Gemini 2.5 Pro/Flash still available as previous generation. Gemini 2.0 Flash/Flash-Lite shutdown date (June 1, 2026) is now imminent — migrate off now.
Alibaba: Qwen3.7-Max (May 20) is the new flagship. Proprietary model; 1M context. Rate limits for Qwen3.7-Max not yet publicly documented — tables below carry forward Qwen3 Max figures as a floor.
Cohere: Command A+ (May 20) replaces Command R+ as the flagship. 218B MoE, 25B active parameters, Apache 2.0 license. Rate limit figures for Command A+ not yet published; the Command R+ figures in the entry paid tier table remain as a reference baseline until Cohere publishes updated limits.

Structural changes:

No new provider additions this edition.
Google’s June 1 Gemini 2.0 shutdown makes the migration window urgent for anything still on 2.0 Flash or 2.0 Flash-Lite endpoints.
Cohere’s Apache 2.0 release of Command A+ means self-hosted deployments are now an option, removing API rate limits entirely for teams with H100 capacity.

What are rate limits?

Rate limits cap how much you can use an API within a given time window. Providers enforce them to manage capacity and ensure fair access. Exceeding a limit returns a 429 Too Many Requests error.

Most providers use the token bucket algorithm: capacity refills continuously up to your maximum, rather than resetting at fixed intervals. A 60 RPM limit means roughly 1 request per second with steady refill, not 60 requests then a hard stop.

The metrics

RPM (Requests per minute): API calls per minute, regardless of size. A 10-token request and a 100K-token request both count as one.
RPD (Requests per day): Daily cap on total API calls. Some providers use this instead of (or alongside) RPM, especially on free tiers.
TPM (Tokens per minute): Total tokens (input + output) processed per minute. Usually the binding constraint in production.
TPD (Tokens per day): Daily token cap. More common on free tiers.
ITPM/OTPM (Input/Output tokens per minute): Anthropic separates input and output token limits, giving finer control. Cached input tokens don’t count toward ITPM on current Claude 4.x models.
ASH/ASD (Audio seconds per hour/day): For speech models like Whisper.

RPM limits set your concurrency ceiling. TPM limits set your throughput. For batch workloads, RPD and TPD matter more. For real-time apps, RPM and TPM hit first.

Free Tier — Requests per Minute (RPM) & Requests per Day (RPD)

Metric	Google			Groq		Cerebras	SambaNova	Fireworks AI	Cohere
Metric	2.5 Pro	2.5 Flash	2.5 Flash-Lite	Llama 4 Scout	Qwen3 32B	Llama 3.3 70B	Llama 3.1 405B	OS models	Command R+*
RPM	5	10	15	30	60	30	10–30	10	20
RPD	50–100	250–1,500	1,000	1,000	1,000	—	—	—	~33†

*Cohere’s free tier figures reference Command R+. Command A+ free tier limits not yet published. †Cohere trial keys get 1,000 calls/month across all endpoints, roughly ~33/day.

Note: OpenAI, Anthropic, xAI, DeepSeek, and Mistral have no free API tier for current flagship models. OpenAI’s free tier does not support any GPT-5.x model (GPT-5.5 Instant is a ChatGPT product, not an API tier). Anthropic’s lowest entry is $5 (Tier 1). xAI and Mistral gate numerical limits behind their respective consoles.

Google migration note: Gemini 2.0 Flash and Flash-Lite shut down June 1, 2026. Any free-tier usage on 2.0 endpoints needs to move to 2.5 Flash or 2.5 Flash-Lite now.

Free Tier — Tokens per Minute (TPM) & Tokens per Day (TPD)

Metric	Google			Groq		Cerebras	SambaNova
Metric	2.5 Pro	2.5 Flash	2.5 Flash-Lite	Llama 4 Scout	Qwen3 32B	Llama 3.3 70B	Llama 3.1 405B
TPM	250,000	250,000	250,000	30,000	6,000	60,000	—
TPD	—	—	—	500,000	500,000	1,000,000	—

Standout: Google still leads with 250K TPM on the free tier, but the RPM/RPD caps (5–15 RPM) mean it’s best for fewer, larger requests. Cerebras offers 60K TPM with 1M TPD and ~2,100 tokens/second inference speed on Llama 3.3 70B, making it the fastest free option by throughput. SambaNova publishes RPM but not TPM/TPD specifics.

Entry Paid Tier — Requests per Minute (RPM) & Requests per Day (RPD)

The tier most developers start with. OpenAI Tier 1 ($5), Anthropic Tier 1 ($5), Google Tier 1 (pay-as-you-go), and others at their lowest paid level.

Metric	OpenAI		Anthropic		Google			xAI	DeepSeek	Fireworks AI	Cohere
Metric	GPT-5.5	GPT-4.1 Nano	Sonnet 4.6	Haiku 4.5	3.1 Pro	2.5 Pro	2.5 Flash	Grok 4.20	V4 Flash	OS models	Command A+*
RPM	500	500	50	50	150†	150	300	Console‡	Dynamic§	≤6,000	500
RPD	—	—	—	—	—†	1,000	1,500	—	—	—	—

*Command A+ entry paid tier limit not yet published. 500 RPM is the Command R+ figure, carried forward as a reference. †Gemini 3.1 Pro is in paid preview. Published limits not confirmed — check AI Studio for your project’s actual limits. ‡xAI publishes tier thresholds ($0/$50/$250/$1K/$5K) but numerical RPM/TPM are only visible in the xAI Console after login. §DeepSeek uses fully dynamic concurrency limits based on server load. No fixed RPM/TPM published.

Mistral note: Mistral also moved to console-only limits. Actual numbers require login at admin.mistral.ai/plateforme/limits. Mistral is excluded from RPM columns where no public figure exists.

Standout: Fireworks can spike to 6,000 RPM but it’s a dynamic ceiling, not guaranteed (soft limit starts at ~1 RPS and doubles hourly). Anthropic’s 50 RPM at Tier 1 is the lowest here, but jumps 20x to 1,000 RPM at Tier 2 ($40).

Entry Paid Tier — Tokens per Minute (TPM)

Metric	OpenAI		Anthropic		Google			DeepSeek
Metric	GPT-5.5	GPT-4.1 Nano	Sonnet 4.6	Haiku 4.5	3.1 Pro	2.5 Pro	2.5 Flash	V4 Flash
TPM	500K	200K	30K in / 8K out	50K in / 10K out	—†	1M	2M	Dynamic

†Gemini 3.1 Pro TPM at entry paid tier not confirmed in public docs — check AI Studio for your project’s actual limits.

Standout: Google 2.5 Flash leads the confirmed figures at 2M TPM. GPT-5.5 gets 500K TPM at Tier 1. Anthropic looks low on paper (30K ITPM for Sonnet), but cached input tokens don’t count toward the limit. With 80% cache hit rate, effective throughput is 5x higher (150K+ effective ITPM).

Scaled Tier — RPM & TPM at Higher Spend

For teams past entry-level. OpenAI Tier 3 ($100+), Anthropic Tier 3 ($200+), Google Tier 2 ($250+).

Metric	OpenAI (Tier 3)		Anthropic (Tier 3)		Google (Tier 2)
Metric	GPT-5.5	GPT-4.1 Nano	Opus 4.x	Haiku 4.5	2.5 Pro	2.5 Flash
RPM	5,000	5,000	2,000	2,000	1,000	2,000
TPM	2M	4M	800K in / 160K out	1M in / 200K out	2M	4M

At the highest standard tiers (OpenAI Tier 5 at $1,000+, Anthropic Tier 4 at $400+):

Metric	OpenAI (Tier 5)		Anthropic (Tier 4)
Metric	GPT-5.5	GPT-4.1 Nano	Opus 4.x	Haiku 4.5
RPM	15,000	30,000	4,000	4,000
TPM	40M	180M	2M in / 400K out	4M in / 800K out

Standout: OpenAI’s Tier 5 numbers remain the highest of any provider with published figures. GPT-4.1 Nano at 180M TPM and 30K RPM is built for high-volume classification and routing. GPT-5.5 gets 15K RPM and 40M TPM. Anthropic’s Tier 4 caps at 4K RPM, but cached tokens don’t count toward ITPM, so effective throughput can be 5x+ higher with good cache hit rates.

Opus pool note: Opus 4.7 and Opus 4.6 share one rate limit bucket. Sending traffic to both model versions doesn’t double your effective limits.

Cerebras & SambaNova

Both specialize in custom silicon for inference speed.

Cerebras

Hardware: Wafer-Scale Engine (WSE-3). Fastest published inference: ~2,100 tokens/second on Llama 3.3 70B.

Tier	RPM	TPM	TPD
Free	30	60,000	1,000,000
Paid	Higher (contact sales)	Higher	Higher

Hosts Llama 3.3 70B, Llama 3.1 8B, and other open models. The speed advantage is real: tasks that take 30 seconds on GPU-based providers finish in under 5 seconds on the WSE-3. Paid tier limits are not publicly documented.

SambaNova

Hardware: Custom RDU (Reconfigurable Dataflow Unit). Best time-to-first-token (TTFT): ~0.2 seconds.

Tier	RPM	Notes
Free	10–30 (varies by model)	Hosts up to Llama 3.1 405B for free

SambaNova is notable for offering Llama 3.1 405B on the free tier. Most other free-tier providers cap out at 70B-class models. TPM and TPD limits are not publicly documented.

Audio Models — ASH & ASD

Groq and Fireworks both publish audio-specific limits.

Metric	Groq (Free Tier)		Fireworks AI
Metric	Whisper Large v3	Whisper Large v3 Turbo	Whisper v3-large	Whisper v3-turbo
RPM	20	20	—	—
RPD	2,000	2,000	—	—
ASH	7,200	7,200	—	—
ASD	28,800	28,800	—	—
Audio min/min	—	—	200	400

Groq: 7,200 ASH = 2 hours of audio per hour of wall time. 28,800 ASD = 8 hours per day. Adequate for a podcast transcription pipeline on the free tier.

Fireworks: 200 min/min for Whisper v3-large, 400 min/min for v3-turbo. Concurrent streaming capped at 10 connections.

Cloud Aggregators — Azure AI & AWS Bedrock

Both use configurable per-deployment limits, not fixed tiers. The shared ratio is 6 RPM per 1,000 TPM.

Azure AI (Microsoft)

Deployment Type	How Limits Work
Pay-as-you-go (Standard)	TPM quota per model per region, auto-scales with usage
Provisioned (PTU)	Reserved throughput units, no per-request limits
Global/Data Zone	Higher default quotas, multi-region routing

Multi-model: admins can select GPT-5.5, GPT-5.4, Claude Opus/Sonnet 4.6, or Gemini 3.1 Pro (verify availability per region — not all models are deployed globally). Azure AI Quotas & Limits

AWS Bedrock

Hosts Claude (Opus 4.7, Sonnet 4.6, Haiku 4.5), Llama 4, Mistral, and Nova models with per-model, per-region quotas. Default quotas vary by model and can be increased via AWS Service Quotas console. Provisioned Throughput deployments remove rate limits entirely. AWS Bedrock Quotas

More Providers — Perplexity, Alibaba (Qwen), Moonshot (Kimi)

Metric	Perplexity			Alibaba (Qwen)			Moonshot
Metric	Sonar Pro	Sonar	Deep Research	Qwen3.7-Max*	Qwen3.5 Plus	Qwen3.5 Flash	Kimi K2.5
RPM (T0)	50	50	5	—			3
RPM (T1)	150	150	10	600*	15,000	15,000	200
RPM (T3+)	1,000	1,000	40	600*	30,000	30,000	5,000
TPM	—	—	—	1M*	5M	10M	—
TPD (T0)	—	—	—	—	—	—	1.5M

*Qwen3.7-Max (May 20) limits not yet formally published. Figures shown are Qwen3 Max limits carried forward as a floor.

Perplexity tiers: T0 = new account, T1 = $50+, T3 = $500+. Alibaba limits shown for international (Singapore) deployment; Beijing deployment is higher (Qwen3 Max jumps to 30K RPM — Qwen3.7-Max Beijing limits unconfirmed). Moonshot T1 = $10+ cumulative recharge; T0 has 1.5M TPD cap, T1+ is unlimited.

Standout: Alibaba’s Qwen3.5 Flash at 30K RPM / 10M TPM (Beijing) remains the highest confirmed throughput of any provider in this post. Moonshot’s T5 tier (10K RPM, 1,000 concurrent connections, $3,000+ recharge) is competitive at the high end.

Provider Notes

OpenAI: GPT-5.5 and GPT-5.4 share identical rate limit profiles across all tiers. GPT-4.1 Nano at Tier 5 (180M TPM, 30K RPM) is the throughput ceiling for any published provider. GPT-5.5 Instant is a ChatGPT product tier — it is not accessible via the API under that name; API access goes through the GPT-5.5 model identifier. GPT-5.4-Cyber is available only to vetted security teams; rate limits not disclosed. GPT-5.2 is being phased out. Batch API offers 50% discount with higher queue limits. Assistants API deprecated August 2026; replaced by Responses API. Docs
Anthropic: Opus 4.7 shares a combined rate limit pool with all Opus 4.x variants. You cannot independently max out Opus 4.7 and 4.6 simultaneously. Cached input tokens don’t count toward ITPM on current 4.x models. No free tier; lowest entry is $5. Fast mode on Opus 4.6 draws from a separate dedicated pool. Claude 3 Haiku retired April 2026. Docs
Google: Static rate limit tables removed from public docs in Q1 2026. Actual limits only visible in AI Studio dashboard (aistudio.google.com/rate-limit). Gemini 3.1 Pro and 3.1 Flash-Lite are in preview with conservative limits. Gemini 2.0 Flash/Flash-Lite shut down June 1, 2026 — this is now days away. Gemini 2.5 Pro/Flash remain available as previous generation. Docs
Groq: Free tier publishes exact numbers (30 RPM, 6K–30K TPM depending on model). Daily token budgets (TPD) alongside TPM. Cached tokens don’t count. Hosts GPT-OSS (20B/120B) and Qwen3-32B on free tier. Runs on custom LPU hardware. Docs
xAI: 5-tier structure ($0/$50/$250/$1K/$5K thresholds) but numerical RPM/TPM only visible in xAI Console. Docs
Mistral: European data residency (GDPR). 5-tier structure (Free through Tier 4 at $500+). Limits enforced per RPS (not RPM), TPM, and tokens/month. Actual numbers require login at admin.mistral.ai. Docs
DeepSeek: Fully dynamic concurrency limits based on server load. No published RPM/TPM. V4-Flash and V4-Pro are the current models. V3.2 aliases deprecated July 24, 2026. V4-Flash pricing: $0.14/M input (cache miss), $0.028/M (cache hit), $0.28/M output. Docs
Cerebras: Fastest inference (~2,100 tok/s on Llama 3.3 70B). Free tier: 30 RPM, 60K TPM, 1M TPD. Paid tier limits not publicly documented. Custom WSE-3 silicon. Docs
SambaNova: Best TTFT (~0.2s). Free tier: 10–30 RPM depending on model size. Hosts up to Llama 3.1 405B for free. TPM and TPD limits not publicly documented. Custom RDU hardware. Docs
Together AI: Dynamic rate limits since January 2026. No fixed tiers or published numbers. Limits grow with sustained usage and are returned in API response headers. Docs
Fireworks AI: Dynamic ceiling up to 6,000 RPM (soft limit starts ~1 RPS, doubles hourly). On-demand GPU deployments remove limits. Spending tier caps: $50–$50K/month by tier. Docs
Cohere: Command A+ (May 20, Apache 2.0, 218B MoE / 25B active) is now the flagship. Runs on 2x H100; self-hosting is viable and removes API rate limits entirely for teams with the hardware. API rate limit figures for Command A+ not yet published — 500 RPM (production chat) shown in tables is the Command R+ figure. Trial keys: 1,000 calls/month. Docs
Perplexity: 6 tiers (T0–T5) based on cumulative spend. Leaky bucket algorithm. Deep Research model has very low limits (5–100 RPM). Agent API: 50–2,000 RPM by tier. Docs
Alibaba (Qwen): Qwen3.7-Max (May 20) is the new flagship; published rate limits not yet confirmed. Region-specific limits apply — Beijing deployment is more generous than Singapore/Global. Qwen3.5 Flash at 30K RPM / 10M TPM (Beijing) is the highest confirmed throughput of any provider listed. Docs
Moonshot (Kimi): 6 tiers (T0–T5). T0 ($1 recharge): 3 RPM, 1 concurrent, 1.5M TPD. T5 ($3,000): 10K RPM, 1,000 concurrent, 5M TPM, unlimited TPD. Automatic 75% caching discount applied without opt-in. Docs
AWS Bedrock: Hosts Claude (Opus 4.7, Sonnet 4.6, Haiku 4.5), Llama 4, Mistral, Nova with per-model per-region quotas. 6 RPM per 1K TPM ratio. Provisioned Throughput removes limits. Docs
Azure AI: Hosts GPT-5.5, GPT-5.4, Claude, and Gemini across regions. PTU deployments remove per-request limits. Verify model availability per region before planning deployments. Docs
NVIDIA NIM: Hosted API is for prototyping (40 RPM). Self-hosted NIM containers have no limits. Docs

Tips for managing rate limits

For a deep dive on token pricing, cost optimization strategies, caching mechanics, model routing architectures, and production cost modeling, see LLM Token Costs and Efficiency. This section covers rate limit management specifically.

Handling 429s

Use exponential backoff when you hit 429s. The Anthropic SDK, OpenAI SDK, and most third-party clients handle this automatically. Don’t build your own retry loop unless you need custom jitter or circuit-breaking behavior.
Check response headers before you hit the wall. Together AI and Fireworks return your current rate limit state in every API response. DeepSeek adjusts concurrency limits dynamically based on server load. Reading these headers in production enables proactive throttling rather than reactive retries.

Caching for throughput (not just cost)

Prompt caching has a rate limit benefit that is separate from its cost benefit. The cost savings are covered in the token costs post. The rate limit implications:

Anthropic: Cached input tokens don’t count toward ITPM limits at all on Claude 4.x models. With 80% cache hit rate, a 2M ITPM limit effectively handles 10M total input tokens per minute. This is a throughput multiplier, not just a cost reduction.
Groq: Cached tokens don’t count toward TPM/TPD limits on the free tier, effectively expanding your daily token budget.
Moonshot (Kimi): Automatic 75% caching discount applied without opt-in. No cache management required.

Batch APIs: higher queue limits

OpenAI, Anthropic, and Google all offer batch endpoints with queue limits that far exceed real-time TPM. OpenAI’s GPT-5.5 gets 1.5M batch queue tokens at Tier 1 vs. 500K real-time TPM. For workloads that don’t need sub-second responses, batch endpoints let you move more tokens through tighter rate limits. See batch API cost savings for pricing details.

Model routing for rate limit distribution

Routing requests to different models by complexity distributes rate limit pressure across multiple buckets instead of concentrating it on your most constrained tier. A three-tier architecture (budget for triage, mid-tier for generation, flagship for reasoning) also cuts costs 60–85%. Full routing architecture with cost modeling is in the token costs post.

Custom silicon for fewer concurrent connections

Cerebras (~2,100 tok/s) and SambaNova (~0.2s TTFT) are faster than GPU-based providers by a large margin. A task that requires 10 parallel GPU-based API calls to meet a latency SLA might need 2–3 calls on Cerebras. Fewer concurrent calls means less rate limit pressure per unit of output.

Self-hosting as an escape hatch

Cohere’s Command A+ (Apache 2.0, 218B MoE / 25B active) runs on 2x H100. For teams already operating H100 capacity, self-hosting removes API rate limits entirely. The economics only work at scale — the hardware cost needs to be weighed against API spend — but it’s now a realistic option for a broader tier of teams than it was six months ago. The same applies to Llama 4, Devstral 2, Mistral Large 3, and other open-weight models.

Watch for shared pools and hidden constraints

Anthropic model pools: Opus 4.7 and 4.6 share one rate limit bucket. Sonnet 4.6 and 4.5 share another. Sending traffic to both model versions doesn’t double your effective limits; it draws from the same pool.
Google’s invisible limits: With static rate limit tables removed from public docs, you must check AI Studio (aistudio.google.com/rate-limit) to see your actual per-project limits. Third-party figures — including those in this post for 2.5 Pro/Flash — are the last confirmed published numbers and may be stale.
DeepSeek’s dynamic ceiling: No published RPM/TPM means no guaranteed minimum. Under heavy load, effective concurrency can drop without warning. Build fallback routing to a second provider if DeepSeek availability is critical to your pipeline.
New model lag: Qwen3.7-Max and Command A+ both launched in late May 2026. Neither provider has published formal rate limit tables for these models yet. Treat the figures in this post for both as provisional floors based on predecessor models.